From 602fe75a1f0a8d64ccb6fc4d69ad510872fdfd13 Mon Sep 17 00:00:00 2001 From: 游雁 <zhifu.gzf@alibaba-inc.com> Date: 星期五, 17 三月 2023 20:30:40 +0800 Subject: [PATCH] rtf benchmark --- funasr/runtime/python/benchmark_onnx.md | 27 +++++++++++++++------------ 1 files changed, 15 insertions(+), 12 deletions(-) diff --git a/funasr/runtime/python/benchmark_onnx.md b/funasr/runtime/python/benchmark_onnx.md index 40075e7..35c7068 100644 --- a/funasr/runtime/python/benchmark_onnx.md +++ b/funasr/runtime/python/benchmark_onnx.md @@ -1,23 +1,26 @@ # Benchmark ### Data set: -Aishell1 test set , the total audio duration is 36108.919 seconds. +Aishell1 [test set](https://www.openslr.org/33/) , the total audio duration is 36108.919 seconds. ### Tools -- Install -```shell -git clone https://github.com/alibaba-damo-academy/FunASR.git && cd FunASR -pip install --editable ./ -cd funasr/runtime/python/utils -pip install -r requirements.txt -``` +- Install ModelScope and FunASR + + ```shell + pip install "modelscope[audio_asr]" --upgrade -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html + git clone https://github.com/alibaba-damo-academy/FunASR.git && cd FunASR + pip install --editable ./ + cd funasr/runtime/python/utils + pip install -r requirements.txt + ``` - recipe -set the model, data path and output_dir -```shell -nohup bash test_rtf.sh &> log.txt & -``` + set the model, data path and output_dir + + ```shell + nohup bash test_rtf.sh &> log.txt & + ``` ## [Paraformer-large](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) -- Gitblit v1.9.1